John Demiris – författare

Robot learning is an exciting and interdisciplinary ?eld. This state is re?ected in the range and form of the papers presented here. Techniques that have - come well established in robot learning are present: evolutionary methods, neural networkapproaches, reinforcement learning; as are techniques from control t- ory, logic programming, and Bayesian statistics. It is notalbe that in many of the papers presented in this volume several of these techniques are employed in conjunction. In papers by Nehmzow, Grossmann and Quoy neural networks are utilised to provide landmark-based representations of the environment, but di?erent techniques are used in each paper to make inferences based on these representations. Biology continues to provide inspiration for the robot learning researcher. In their paper Peter Eggenberger et al. borrow ideas about the role of n- romodulators in switching neural circuits, These are combined with standard techniques from arti?cial neural networks and evolutionary computing to p- vide a powerful new algorithm for evolving robot controllers. In the ?nal paper in this volume Bianco and Cassinis combine observations about the navigation behaviour of insects with techniques from control theory to produce their visual landmarklearning system.Hopefully this convergence of engineering and biol- ical approaches will continue. A rigourous understanding of the ways techniques from these very di?erent disciplines can be fused is an important challenge if progress is to continue. Al these papers are also testament to the utility of using robots to study intelligence and adaptive behaviour.

Robot learning is a broad and interdisciplinary area. This holds with regard to the basic interests and the scienti c background of the researchers involved, as well as with regard to the techniques and approaches used. The interests that motivate the researchers in this eld range from fundamental research issues, such as how to constructively understand intelligence, to purely application o- ented work, such as the exploitation of learning techniques for industrial robotics. Given this broad scope of interests, it is not surprising that, although AI and robotics are usually the core of the robot learning eld, disciplines like cog- tive science, mathematics, social sciences, neuroscience, biology, and electrical engineering have also begun to play a role in it. In this way, its interdisciplinary character is more than a mere fashion, and leads to a productive exchange of ideas. One of the aims of EWLR-6 was to foster this exchange of ideas and to f- ther boost contacts between the di erent scienti c areas involved in learning robots. EWLR is, traditionally, a \European Workshop on Learning Robots". Nevertheless, the organizers of EWLR-6 decided to open up the workshop to non-European research as well, and included in the program committee we- known non-European researchers. This strategy proved to be successful since there was a strong participation in the workshop from researchers outside - rope, especially from Japan, which provided new ideas and lead to new contacts.